All of lore.kernel.org
 help / color / mirror / Atom feed
From: David Disseldorp <ddiss@suse.de>
To: Christoph Hellwig <hch@infradead.org>
Cc: target-devel@vger.kernel.org, linux-scsi@vger.kernel.org,
	martin.petersen@oracle.com, bvanassche@acm.org
Subject: Re: [RFC PATCH 5/5] scsi: target: avoid XCOPY per-loop read/write cmd allocations
Date: Thu, 26 Mar 2020 21:20:44 +0000	[thread overview]
Message-ID: <20200326222044.06e3d5c9@suse.de> (raw)
In-Reply-To: <20200324092323.GE18399@infradead.org>

Hi Christoph,

Thanks for the feedback...

On Tue, 24 Mar 2020 02:23:23 -0700, Christoph Hellwig wrote:

> On Mon, Mar 23, 2020 at 05:54:10PM +0100, David Disseldorp wrote:
> > Reads and writes in the XCOPY loop are synchronous, so needn't be
> > allocated / freed with each loop.  
> 
> That is true, but I think with your previous cleanups we can easily
> go one step further and just allocate a single command and sense buffer
> directly in struct xcopy_op, and just have local completions on the
> stack.

I'm probably missing something, but having the (stack) completion
separate to the se_cmd and sense buffer would mean that it's no longer a
straightforward container_of() in the .check_stop_free() callback.

I've reworked this patch to put the entire xcopy_pt_cmd on the stack and
will send it out with v2.

Cheers, David

WARNING: multiple messages have this Message-ID (diff)
From: David Disseldorp <ddiss@suse.de>
To: Christoph Hellwig <hch@infradead.org>
Cc: target-devel@vger.kernel.org, linux-scsi@vger.kernel.org,
	martin.petersen@oracle.com, bvanassche@acm.org
Subject: Re: [RFC PATCH 5/5] scsi: target: avoid XCOPY per-loop read/write cmd allocations
Date: Thu, 26 Mar 2020 22:20:44 +0100	[thread overview]
Message-ID: <20200326222044.06e3d5c9@suse.de> (raw)
In-Reply-To: <20200324092323.GE18399@infradead.org>

Hi Christoph,

Thanks for the feedback...

On Tue, 24 Mar 2020 02:23:23 -0700, Christoph Hellwig wrote:

> On Mon, Mar 23, 2020 at 05:54:10PM +0100, David Disseldorp wrote:
> > Reads and writes in the XCOPY loop are synchronous, so needn't be
> > allocated / freed with each loop.  
> 
> That is true, but I think with your previous cleanups we can easily
> go one step further and just allocate a single command and sense buffer
> directly in struct xcopy_op, and just have local completions on the
> stack.

I'm probably missing something, but having the (stack) completion
separate to the se_cmd and sense buffer would mean that it's no longer a
straightforward container_of() in the .check_stop_free() callback.

I've reworked this patch to put the entire xcopy_pt_cmd on the stack and
will send it out with v2.

Cheers, David

  reply	other threads:[~2020-03-26 21:20 UTC|newest]

Thread overview: 24+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-03-23 16:54 [RFC PATCH 0/5] scsi: target: XCOPY performance David Disseldorp
2020-03-23 16:54 ` David Disseldorp
2020-03-23 16:54 ` [RFC PATCH 1/5] scsi: target: use #def for xcopy descriptor len David Disseldorp
2020-03-23 16:54   ` David Disseldorp
2020-03-24  9:06   ` Christoph Hellwig
2020-03-24  9:06     ` Christoph Hellwig
2020-03-23 16:54 ` [RFC PATCH 2/5] scsi: target: drop xcopy DISK BLOCK LENGTH debug David Disseldorp
2020-03-23 16:54   ` David Disseldorp
2020-03-24  9:07   ` Christoph Hellwig
2020-03-24  9:07     ` Christoph Hellwig
2020-03-23 16:54 ` [RFC PATCH 3/5] scsi: target: avoid per-loop XCOPY buffer allocations David Disseldorp
2020-03-23 16:54   ` David Disseldorp
2020-03-24  9:16   ` Christoph Hellwig
2020-03-24  9:16     ` Christoph Hellwig
2020-03-23 16:54 ` [RFC PATCH 4/5] scsi: target: increase XCOPY I/O size David Disseldorp
2020-03-23 16:54   ` David Disseldorp
2020-03-24  9:16   ` Christoph Hellwig
2020-03-24  9:16     ` Christoph Hellwig
2020-03-23 16:54 ` [RFC PATCH 5/5] scsi: target: avoid XCOPY per-loop read/write cmd allocations David Disseldorp
2020-03-23 16:54   ` David Disseldorp
2020-03-24  9:23   ` Christoph Hellwig
2020-03-24  9:23     ` Christoph Hellwig
2020-03-26 21:20     ` David Disseldorp [this message]
2020-03-26 21:20       ` David Disseldorp

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20200326222044.06e3d5c9@suse.de \
    --to=ddiss@suse.de \
    --cc=bvanassche@acm.org \
    --cc=hch@infradead.org \
    --cc=linux-scsi@vger.kernel.org \
    --cc=martin.petersen@oracle.com \
    --cc=target-devel@vger.kernel.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body. 
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.